Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with the concept of 'lower' or 'lowering'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     higher
    -0.18
     above
    -0.16
    ift
    -0.16
     up
    -0.15
    aml
    -0.15
    ute
    -0.15
     little
    -0.15
    roke
    -0.14
    aman
    -0.14
    aya
    -0.14
    POSITIVE LOGITS
    cased
    0.22
    _than
    0.20
    Than
    0.19
    archy
    0.19
    most
    0.19
    -than
    0.19
    -middle
    0.18
    anging
    0.18
    enstein
    0.18
    EST
    0.17
    Act Density 0.029%

    No Known Activations